dust-tt / llama-sspLinks
Experiments on speculative sampling with Llama models
☆128Updated 2 years ago
Alternatives and similar repositories for llama-ssp
Users that are interested in llama-ssp are comparing it to the libraries listed below
Sorting:
- Multipack distributed sampler for fast padding-free training of LLMs☆199Updated last year
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆206Updated last year
- ☆202Updated 9 months ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆223Updated last year
- Manage scalable open LLM inference endpoints in Slurm clusters☆271Updated last year
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- Pre-training code for Amber 7B LLM☆167Updated last year
- Code repository for the c-BTM paper☆107Updated last year
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆137Updated 2 years ago
- scalable and robust tree-based speculative decoding algorithm☆355Updated 7 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆155Updated 5 months ago
- ☆127Updated last year
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"☆310Updated last year
- batched loras☆345Updated 2 years ago
- Data preparation code for Amber 7B LLM☆91Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated 11 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆145Updated last year
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆96Updated 2 years ago
- A pipeline for LLM knowledge distillation☆107Updated 5 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆200Updated last year
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆80Updated last year
- BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.☆211Updated last week
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe …☆158Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated 10 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆207Updated 9 months ago
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆103Updated 2 years ago
- experiments with inference on llama☆104Updated last year
- ☆565Updated last year